Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.

AI code reviews grounded in 12 classic engineering books — decay risk diagnostics with book citations, severity labels, and 6 analysis modes including full-sweep auto-fix

Zero-dependency codebase intelligence for AI agents and humans. Static analysis → structured Markdown → readable by any LLM. 8 code health agents included.

Logic-first AI code review via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Catches behavioral bugs, type-contract breaches & async hazards that linters miss. Six skills · Claude Code · Codex CLI · Gemini CLI.

Nine quality-canary skills for AI coding agents - code health, grounding, supply chain, resilience, drift & more. Cross-agent, consent-gated, token-lean.

🩺 Application Checkup — a portable, tool-agnostic scanner for codebase health, quality, security & hygiene. Runs anywhere (incl. Docker), degrades gracefully, emits a normalised report.

Calculate a health score for any Git repository. Analyzes complexity, docs, tests, deps, and collaboration.

Claude Code skills that catch AI slop, technical debt & architecture drift before they reach production — plan, rules, audit, fix, docs.

Visualize your Python codebase health and architecture as an auto-updating SVG in your README.

The open code health benchmark — paste any github.com URL, or just replace github.com with stackhealth.dev. Scores security, quality, hygiene & community via a fully open formula. Free forever.

A self-maintaining repo immune system for Claude Code — 14 auditing 'healers' that detect drift, fix the mechanical, and prevent recurrence. Plugin in development; live preview inside.

An electric pet. Take care of your TOMO and your codebases at the same time.

Your private developer-efficiency report from git history — 11 dimensions (DORA / SPACE / CodeScene), local & read-only, narrated by an LLM.

Codebase Health Audit Prompt

Deterministic 0-100 health score and agent fix-loop for Android Jetpack Compose. Wraps detekt + compose-rules

프로젝트 주치의 — AI로 만들다 엉킨 프로젝트를, 비개발자도 읽을 수 있는 진단 보고서로 바꿔주는 Claude Code 스킬

(WIP) Lightweight, self-hosted C# code-health monitor (ML-trained trend detector).

Interactive codebase health audit. 8 dimensions: Architecture, Security, Performance, Maintainability, Testing, Docs, Dependencies, Quality. Zero dependencies.

AI-powered GitHub repository knowledge risk analyzer that identifies bus factor, ownership concentration, and risky files.